diff --git a/CHANGELOG.md b/CHANGELOG.md
index 76347bd2f8b..195717ee4ef 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -39,6 +39,7 @@ Docs: https://docs.openclaw.ai
 
 ### Fixes
 
+- Gateway/model pricing: fetch OpenRouter and LiteLLM pricing asynchronously at startup and extend catalog fetch timeouts to 30 seconds, reducing noisy timeout warnings during slow upstream responses.
 - Status: show `Fast` in `/status` when fast mode is enabled, including config/default-derived fast mode, and omit it when disabled.
 - Models/auth: merge provider-owned default-model additions from `openclaw models auth login` instead of replacing `agents.defaults.models`, so re-authenticating an OAuth provider such as OpenAI Codex no longer wipes other providers' aliases and per-model params. Migrations that must rename keys (Anthropic -> Claude CLI) opt in with `replaceDefaultModels`. Fixes #69414. (#70435) Thanks @neeravmakwana.
 - Media understanding/audio: prefer configured or key-backed STT providers before auto-detected local Whisper CLIs, so installed local transcription tools no longer shadow API providers such as Groq/OpenAI in `tools.media.audio` auto mode. Fixes #68727.
diff --git a/src/gateway/model-pricing-cache.test.ts b/src/gateway/model-pricing-cache.test.ts
index 85e93fa7faf..bfdfc6713d4 100644
--- a/src/gateway/model-pricing-cache.test.ts
+++ b/src/gateway/model-pricing-cache.test.ts
@@ -19,6 +19,7 @@ import {
   collectConfiguredModelPricingRefs,
   getCachedGatewayModelPricing,
   refreshGatewayModelPricingCache,
+  startGatewayModelPricingRefresh,
 } from "./model-pricing-cache.js";
 
 describe("model-pricing-cache", () => {
@@ -519,6 +520,39 @@ describe("model-pricing-cache", () => {
     });
   });
 
+  it("defers bootstrap refresh work until after the starter returns", async () => {
+    const config = {
+      agents: {
+        defaults: {
+          model: { primary: "anthropic/claude-opus-4-6" },
+        },
+      },
+    } as unknown as OpenClawConfig;
+    const fetchImpl = withFetchPreconnect(
+      vi.fn(async (input: RequestInfo | URL) => {
+        const url =
+          typeof input === "string" ? input : input instanceof URL ? input.href : input.url;
+        if (url.includes("openrouter.ai")) {
+          return new Response(JSON.stringify({ data: [] }), {
+            status: 200,
+            headers: { "Content-Type": "application/json" },
+          });
+        }
+        return new Response(JSON.stringify({}), {
+          status: 200,
+          headers: { "Content-Type": "application/json" },
+        });
+      }),
+    );
+
+    const stop = startGatewayModelPricingRefresh({ config, fetchImpl });
+
+    expect(fetchImpl).not.toHaveBeenCalled();
+    await vi.dynamicImportSettled();
+    expect(fetchImpl).toHaveBeenCalled();
+    stop();
+  });
+
   it("logs configured timeout seconds when pricing fetches time out", async () => {
     const warnings: string[] = [];
     loggingState.rawConsole = {
@@ -549,10 +583,10 @@ describe("model-pricing-cache", () => {
     expect(warnings).toEqual(
       expect.arrayContaining([
         expect.stringContaining(
-          "OpenRouter pricing fetch failed (timeout 15s): TimeoutError: The operation was aborted due to timeout",
+          "OpenRouter pricing fetch failed (timeout 30s): TimeoutError: The operation was aborted due to timeout",
         ),
         expect.stringContaining(
-          "LiteLLM pricing fetch failed (timeout 15s): TimeoutError: The operation was aborted due to timeout",
+          "LiteLLM pricing fetch failed (timeout 30s): TimeoutError: The operation was aborted due to timeout",
         ),
       ]),
     );
diff --git a/src/gateway/model-pricing-cache.ts b/src/gateway/model-pricing-cache.ts
index 661a7aac1d1..c3712ff8b11 100644
--- a/src/gateway/model-pricing-cache.ts
+++ b/src/gateway/model-pricing-cache.ts
@@ -40,7 +40,7 @@ const OPENROUTER_MODELS_URL = "https://openrouter.ai/api/v1/models";
 const LITELLM_PRICING_URL =
   "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json";
 const CACHE_TTL_MS = 24 * 60 * 60_000;
-const FETCH_TIMEOUT_MS = 15_000;
+const FETCH_TIMEOUT_MS = 30_000;
 const MAX_PRICING_CATALOG_BYTES = 5 * 1024 * 1024;
 const PROVIDER_ALIAS_TO_OPENROUTER: Record<string, string> = {
   "google-gemini-cli": "google",
@@ -655,10 +655,17 @@ export function startGatewayModelPricingRefresh(params: {
   config: OpenClawConfig;
   fetchImpl?: typeof fetch;
 }): () => void {
-  void refreshGatewayModelPricingCache(params).catch((error: unknown) => {
-    log.warn(`pricing bootstrap failed: ${String(error)}`);
+  let stopped = false;
+  queueMicrotask(() => {
+    if (stopped) {
+      return;
+    }
+    void refreshGatewayModelPricingCache(params).catch((error: unknown) => {
+      log.warn(`pricing bootstrap failed: ${String(error)}`);
+    });
   });
   return () => {
+    stopped = true;
     clearRefreshTimer();
   };
 }